Agent Skills Hub

cosense

A comprehensive automation skill for Cosense (formerly Scrapbox) enabling page reading, searching, creating, and safe editing via API.

claude

Anthropic Claude AI models for high-performance coding, large-context analysis, and GUI interaction.

deep-research

A systematic, multi-angle web research agent. Use for deep investigation, complex queries, and as a mandatory pre-research step before content generation to ensure evidence-backed, high-quality results.

entry-point-analyzer

Map the attack surface of smart contract codebases by identifying and categorizing state-changing entry points.

toh-framework

Security-first auditing framework for AI-generated code. Provides multi-level protection including hardcoded secret detection, dangerous pattern identification, and comprehensive vulnerability audits for modern web applications.

proofread

Automated, non-destructive proofreading for LaTeX and Quarto lecture files, generating quality reports for grammar, typos, and academic style.

guard

Epistemic safety analysis for JSON data in prompts to prevent LLM hallucinations and reasoning errors when handling incomplete or large-scale datasets.

seer

macOS visual automation tool for precise window capture, video recording, UI mockup annotation, Excalidraw wireframing, and automated visual regression testing.

huginn-onboard

Bridge assets from EVM chains to Starknet, deploy agent accounts, and register identities with the HuginnRegistry for autonomous AI agent onboarding.

prompt-injection-test

A testing utility designed to simulate prompt injection attacks and validate security scanners for AI agent skills.

mod-actions

A comprehensive moderation toolkit for Civitai, providing automated user management, strike systems, image review, content regulation, and CSAM reporting via tRPC API.

native-app-performance

Native macOS/iOS app performance profiling via xctrace and CLI-based hotspot analysis without opening the Instruments UI.